Diffusers Image Outpaint

Diffusers Image Outpaint

Extends a picture past its edges by filling in new content around it, in a Gradio app built on Stable Diffusion XL models. It suits anyone who needs more canvas.

Made by fffiloni on Hugging Face. These notes are Mindket's, written from its Space page and README; the app's own files and license are on Hugging Face.

About

What it is: Diffusers Image Outpaint is a Gradio app that grows an image beyond its original borders. It builds the extra area with SDXL-based models, including a RealVisXL Lightning checkpoint and a ControlNet union model. It runs on GPU hardware at Hugging Face and carries an MCP label.

Who it suits: People who have a picture that is cropped too tight or in the wrong shape and want more room around the subject.

Industry | Who uses it | How they use it | Example
Design | Graphic designers | Widen a picture to fit a banner layout | Add space on both sides of a product photo
Photography | Photographers | Recover room lost to a tight crop | Extend the sky above an outdoor shot
Marketing | Social media teams | Reshape one image for several formats | Turn a square image into a wide one
Software | Developers | Study how outpainting is wired with diffusers | Read pipeline_fill_sd_xl.py

People who only need to resize or crop a picture can skip it.

Where to use it:

• A browser, by visiting the Space on Hugging Face
• A computer of your own that runs Windows, macOS or Linux and has Python 3.10
• An MCP client, since the Space carries the MCP label, although the source gives no connection steps

Use case | Who | What they get back
Expand an image | Designers and photographers | A picture with new content filled in around its edges
Try outpainting models | Developers | A working example built on diffusers

How to set it up:

• Python 3.10 and pip on Windows, macOS or Linux
• The Python packages in requirements.txt
• Gradio 6.14.0, the version the Space uses
• A GPU, since the Space is set to zero-a10g

1. Install the Hugging Face hub package.
2. Download the Space with the hf command.
3. Move into the new folder.
4. Install gradio at the version the Space uses, then the listed packages.
5. Start the app with Python.

pip install -U huggingface_hub
hf download fffiloni/diffusers-image-outpaint --repo-type space --local-dir diffusers-image-outpaint
cd diffusers-image-outpaint
pip install gradio==6.14.0
pip install -r requirements.txt
python app.py

How to use it: Online, visit the Space on Hugging Face, give it an image and choose how to expand it. On your own computer, run the start command and open the local page Gradio serves.

python app.py

Tool | What it does
app.py | Starts the Gradio interface
pipeline_fill_sd_xl.py | Holds the fill pipeline for SDXL
controlnet_union.py | Holds the ControlNet union model code
examples | Holds sample images to try

Example: You upload a photo of a building cropped at the roof and ask for more space above it. The app fills the new area and gives back a larger picture.

For newcomers and experts: If you are new, start with one of the sample images in the examples folder. Outpainting means asking a model to draw the part of a scene that lies beyond the frame.

If you know the field, the Space combines RealVisXL_V5.0_Lightning, sdxl-vae-fp16-fix and xinsir's controlnet-union-sdxl-1.0 with T2I-Adapter, using a custom fill pipeline for SDXL. It runs on the zero-a10g hardware setting. The trade-off is a GPU requirement, and results depend on the model.

You give the app an image
You choose how far to expand it
The SDXL pipeline fills the new area
You get the larger picture back

Good to know:

• Hardware: the Space is set to zero-a10g, so a local copy needs a GPU too
• Models: it names four models on Hugging Face
• MCP: the Space carries the MCP label
• License: apache-2
• Cost to run: GPU hardware, no API key or paid service is named
• Data it reaches: the images you give it and the models it fetches from Hugging Face

On Hugging Face, 13 November 2026

• Likes: 2,565
• Built with: gradio
• License: apache-2.0

Links

• Space: https://huggingface.co/spaces/fffiloni/diffusers-image-outpaint
• Files: https://huggingface.co/spaces/fffiloni/diffusers-image-outpaint/tree/main

Try it

Open the Space in your browser, or copy it to your own Hugging Face account from its page. Nothing in this kit runs by itself.